<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Gui-Agents on MLLog.dev</title><link>https://mllog.dev/pl/tags/gui-agents/</link><description>Recent content in Gui-Agents on MLLog.dev</description><image><title>MLLog.dev</title><url>https://mllog.dev/images/default_mllog.png</url><link>https://mllog.dev/images/default_mllog.png</link></image><generator>Hugo -- 0.147.9</generator><language>pl</language><lastBuildDate>Wed, 15 Apr 2026 10:00:00 +0100</lastBuildDate><atom:link href="https://mllog.dev/pl/tags/gui-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>ClawGUI: Otwarty full-stack pipeline dla agentów GUI</title><link>https://mllog.dev/pl/posts/2026-04-15-clawgui-unified-framework-gui-agents/</link><pubDate>Wed, 15 Apr 2026 10:00:00 +0100</pubDate><guid>https://mllog.dev/pl/posts/2026-04-15-clawgui-unified-framework-gui-agents/</guid><description>ClawGUI łączy online RL, odtwarzalną ewaluację i deploy agentów GUI na realnych urządzeniach w jeden otwarty pipeline — i pokazuje, że trenowany w nim model 2B bije nietrenowane modele 72B na MobileWorld.</description></item></channel></rss>